Setting the file. One moment.
Chapter 36 · Microsoft Foundry
Subchapter 36.104
foundry-agent/trace/references/conversation-detail.mdMarkdown4 KBView on GitHub
Reconstruct the complete span tree for a single conversation to see exactly what happened: every LLM call, tool execution, and agent invocation with timing, tokens, and errors.
Use operation_Id (trace ID) to get all spans in a single request:
dependencies
| where operation_Id == "<operation_id>"
| project timestamp, name, duration, resultCode, success,
spanId = id,
parentSpanId = operation_ParentId,
operation = tostring(customDimensions["gen_ai.operation.name"]),
model = tostring(customDimensions["gen_ai.request.model"]),
responseModel = tostring(customDimensions["gen_ai.response.model"]),
inputTokens = toint(customDimensions["gen_ai.usage.input_tokens"]),
outputTokens = toint(customDimensions["gen_ai.usage.output_tokens"]),
responseId = tostring(customDimensions["gen_ai.response.id"]),
finishReason = tostring(customDimensions["gen_ai.response.finish_reasons"]),
errorType = tostring(customDimensions["error.type"]),
toolName = tostring(customDimensions["gen_ai.tool.name"]),
toolCallId = tostring(customDimensions["gen_ai.tool.call.id"])
| order by timestamp ascAlso fetch the parent request:
requests
| where operation_Id == "<operation_id>"
| project timestamp, name, duration, resultCode, success, id, operation_ParentIdUse spanId and parentSpanId to reconstruct the hierarchy:
invoke_agent (root) ─── 4200ms
├── chat (LLM call #1) ─── 1800ms, gpt-4o, 450→120 tokens
│ └── [output: "Let me check the weather..."]
├── execute_tool (get_weather) [tool: remote_functions.weather_api] ─── 200ms
│ └── [result: "rainy, 57°F"]
├── chat (LLM call #2) ─── 1500ms, gpt-4o, 620→85 tokens
│ └── [output: "The weather in Paris is rainy, 57°F"]
└── [total: 450+620=1070 input, 120+85=205 output tokens]Present as an indented tree with:
The full input/output content lives on invoke_agent dependency spans in gen_ai.input.messages and gen_ai.output.messages. These JSON arrays contain the complete conversation (system prompt, user query, assistant response):
dependencies
| where operation_Id == "<operation_id>"
| where customDimensions["gen_ai.operation.name"] == "invoke_agent"
| project timestamp,
inputMessages = tostring(customDimensions["gen_ai.input.messages"]),
outputMessages = tostring(customDimensions["gen_ai.output.messages"])
| order by timestamp ascMessage structure: [{"role": "user", "parts": [{"type": "text", "content": "..."}]}]
Also check the traces table for additional GenAI log events:
traces
| where operation_Id == "<operation_id>"
| where message contains "gen_ai"
| project timestamp, message, customDimensions
| order by timestamp ascexceptions
| where operation_Id == "<operation_id>"
| project timestamp, type, message, outerMessage,
details = parse_json(details)
| order by timestamp ascPresent exceptions inline in the span tree at their position in the timeline.
See Eval Correlation for the full workflow to look up evaluation scores by response ID or conversation ID. Use gen_ai.response.id values from Step 1 spans to correlate.